This example isn't using gpt embeddings but it could. It's using local Hugging Face models (FLAN-T5) with a context provided by a vector store (Faiss).
Answer the following question using only the context below. Say 'no answer' when the question can't be answered. Question: {question} Context: {context}
Not sure this prompt works for all scenarios and models. But it can easily be changed and is a starting point.